File size: 23,258 Bytes
d1ceb73 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 |
# Generated content DO NOT EDIT
class PreTokenizer:
"""
Base class for all pre-tokenizers
This class is not supposed to be instantiated directly. Instead, any implementation of a
PreTokenizer will return an instance of this class when instantiated.
"""
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class BertPreTokenizer(PreTokenizer):
"""
BertPreTokenizer
This pre-tokenizer splits tokens on spaces, and also on punctuation.
Each occurence of a punctuation character will be treated separately.
"""
def __init__(self):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class ByteLevel(PreTokenizer):
"""
ByteLevel PreTokenizer
This pre-tokenizer takes care of replacing all bytes of the given string
with a corresponding representation, as well as splitting into words.
Args:
add_prefix_space (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether to add a space to the first word if there isn't already one. This
lets us treat `hello` exactly like `say hello`.
use_regex (:obj:`bool`, `optional`, defaults to :obj:`True`):
Set this to :obj:`False` to prevent this `pre_tokenizer` from using
the GPT2 specific regexp for spliting on whitespace.
"""
def __init__(self, add_prefix_space=True, use_regex=True):
pass
@staticmethod
def alphabet():
"""
Returns the alphabet used by this PreTokenizer.
Since the ByteLevel works as its name suggests, at the byte level, it
encodes each byte value to a unique visible character. This means that there is a
total of 256 different characters composing this alphabet.
Returns:
:obj:`List[str]`: A list of characters that compose the alphabet
"""
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class CharDelimiterSplit(PreTokenizer):
"""
This pre-tokenizer simply splits on the provided char. Works like `.split(delimiter)`
Args:
delimiter: str:
The delimiter char that will be used to split input
"""
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class Digits(PreTokenizer):
"""
This pre-tokenizer simply splits using the digits in separate tokens
Args:
individual_digits (:obj:`bool`, `optional`, defaults to :obj:`False`):
If set to True, digits will each be separated as follows::
"Call 123 please" -> "Call ", "1", "2", "3", " please"
If set to False, digits will grouped as follows::
"Call 123 please" -> "Call ", "123", " please"
"""
def __init__(self, individual_digits=False):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class Metaspace(PreTokenizer):
"""
Metaspace pre-tokenizer
This pre-tokenizer replaces any whitespace by the provided replacement character.
It then tries to split on these spaces.
Args:
replacement (:obj:`str`, `optional`, defaults to :obj:`▁`):
The replacement character. Must be exactly one character. By default we
use the `▁` (U+2581) meta symbol (Same as in SentencePiece).
prepend_scheme (:obj:`str`, `optional`, defaults to :obj:`"always"`):
Whether to add a space to the first word if there isn't already one. This
lets us treat `hello` exactly like `say hello`.
Choices: "always", "never", "first". First means the space is only added on the first
token (relevant when special tokens are used or other pre_tokenizer are used).
"""
def __init__(self, replacement="_", prepend_scheme="always", split=True):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class Punctuation(PreTokenizer):
"""
This pre-tokenizer simply splits on punctuation as individual characters.
Args:
behavior (:class:`~tokenizers.SplitDelimiterBehavior`):
The behavior to use when splitting.
Choices: "removed", "isolated" (default), "merged_with_previous", "merged_with_next",
"contiguous"
"""
def __init__(self, behavior="isolated"):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class Sequence(PreTokenizer):
"""
This pre-tokenizer composes other pre_tokenizers and applies them in sequence
"""
def __init__(self, pretokenizers):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class Split(PreTokenizer):
"""
Split PreTokenizer
This versatile pre-tokenizer splits using the provided pattern and
according to the provided behavior. The pattern can be inverted by
making use of the invert flag.
Args:
pattern (:obj:`str` or :class:`~tokenizers.Regex`):
A pattern used to split the string. Usually a string or a a regex built with `tokenizers.Regex`
behavior (:class:`~tokenizers.SplitDelimiterBehavior`):
The behavior to use when splitting.
Choices: "removed", "isolated", "merged_with_previous", "merged_with_next",
"contiguous"
invert (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to invert the pattern.
"""
def __init__(self, pattern, behavior, invert=False):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class UnicodeScripts(PreTokenizer):
"""
This pre-tokenizer splits on characters that belong to different language family
It roughly follows https://github.com/google/sentencepiece/blob/master/data/Scripts.txt
Actually Hiragana and Katakana are fused with Han, and 0x30FC is Han too.
This mimicks SentencePiece Unigram implementation.
"""
def __init__(self):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class Whitespace(PreTokenizer):
"""
This pre-tokenizer simply splits using the following regex: `\w+|[^\w\s]+`
"""
def __init__(self):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
class WhitespaceSplit(PreTokenizer):
"""
This pre-tokenizer simply splits on the whitespace. Works like `.split()`
"""
def __init__(self):
pass
def pre_tokenize(self, pretok):
"""
Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
This method allows to modify a :class:`~tokenizers.PreTokenizedString` to
keep track of the pre-tokenization, and leverage the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you just want to see the result of
the pre-tokenization of a raw string, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize_str`
Args:
pretok (:class:`~tokenizers.PreTokenizedString):
The pre-tokenized string on which to apply this
:class:`~tokenizers.pre_tokenizers.PreTokenizer`
"""
pass
def pre_tokenize_str(self, sequence):
"""
Pre tokenize the given string
This method provides a way to visualize the effect of a
:class:`~tokenizers.pre_tokenizers.PreTokenizer` but it does not keep track of the
alignment, nor does it provide all the capabilities of the
:class:`~tokenizers.PreTokenizedString`. If you need some of these, you can use
:meth:`~tokenizers.pre_tokenizers.PreTokenizer.pre_tokenize`
Args:
sequence (:obj:`str`):
A string to pre-tokeize
Returns:
:obj:`List[Tuple[str, Offsets]]`:
A list of tuple with the pre-tokenized parts and their offsets
"""
pass
|